The Visual Computer

, Volume 29, Issue 4, pp 311–321 | Cite as

Robust image metamorphosis immune from ghost and blur

  • Enhua Wu
  • Feitong Liu
Original Article


In this paper, we propose a novel method for the metamorphosis between two different images. By the approach, the transition sequence is generated by stitching two forward and backward warped sequences in a three-dimensional space along transition surface. In contrast to the traditional methods by blending two warped images at each intermediate frame, we continuously warp images on opposite direction without blending until the two warped images match in a three-dimensional space leading to a better transition in quality. Furthermore, for each pixel, we make decision of choosing a given input image best suitable so as to produce plausible in-between images to prevent from ghost and blur. By our scheme, the transition surface is computed by minimizing an energy function in terms of graph-cut optimization. Depending on the transition surface, a warp function is proposed to create a smooth and clear transformation. We demonstrate the advantage of our framework by performing transformation test to various kinds of image couples.


Image morphing Warping Animation Graph cut 



Support to the research has been from the National Fundamental S&T Research Grant 973 Program (2009CB320802, 2011CB302801), the NSFC grant (60833007), and the Research Grant of University of Macau.


  1. 1.
    Beier, T., Neely, S.: Feature-based image metamorphosis. ACM SIGGRAPH Comput. Graph. 26(2), 35–42 (1992) (Proceedings of SIGGRAPH 92) CrossRefGoogle Scholar
  2. 2.
    Nishita, T., Fujii, T., Nakamae, E.: Metamorphosis using Bezier clipping. In: Proceedings of PCCGA 93, pp. 162–173 (1993) Google Scholar
  3. 3.
    Wolberg, G.: Digital Image Warping. IEEE Computer Society Press, Washington (1990) Google Scholar
  4. 4.
    Lee, S., Chwa, K.Y., Hahn, J., Shin, S.Y.: Image morphing using deformation techniques. J. Vis. Comput. Animat. 7, 3–23 (1996) CrossRefGoogle Scholar
  5. 5.
    Hu, S.M., Li, C.F., Zhang, H.: Actual morphing: a physics-based approach to blending. In: Proceedings of ACM SMA 04, pp. 309–314 (1994) Google Scholar
  6. 6.
    Stich, T., Linz, C., Wallraven, C., Cunningham, D., Magnor, M.: Perception-motivated interpolation of image sequences. ACM Trans. Appl. Percept. 8(2), 1–25 (2011) CrossRefGoogle Scholar
  7. 7.
    Mahajan, D., Huang, F., Matusik, W., Ramorthi, R., Belhumeur, P.: Moving gradients: a path-based method for plausible image interpolation. ACM Trans. Graph. 28(3), 42:1–42:11 (2009) (SIGGRAPH 09) CrossRefGoogle Scholar
  8. 8.
    Wolberg, G.: Image morphing: a survey. Vis. Comput. 14, 360–372 (1998) CrossRefGoogle Scholar
  9. 9.
    Karam, H., Hassanien, A., Nakajima, M.: Feature-based image metamorphosis optimization algorithm. In: Proceedings of VSMM 01, pp. 555–564 (2001) Google Scholar
  10. 10.
    Lee, S., Chwa, K.Y., Hahn, J., Shin, S.Y., Wolberg, G.: Image metamorphosis using snakes and free-form deformations. In: Proceedings of SIGGRAPH 95, pp. 439–448 (1995) CrossRefGoogle Scholar
  11. 11.
    Litwinowicz, P., Williams, L.: Animating images with drawings. In: Proceedings of SIGGRAPH 94, pp. 409–412 (1994) CrossRefGoogle Scholar
  12. 12.
    Stich, T., Linz, C., Albuquerque, G., Magnor, M.: View and time interpolation in image space. Comput. Graph. Forum 27(7), 1781–1787 (2008) CrossRefGoogle Scholar
  13. 13.
    Stich, T., Magnor, M.: Image morphing for space-time interpolation. Computer Graphic Lab, TU Braunschweig, Technical Report (2007) Google Scholar
  14. 14.
    Lerios, A., Garfinkle, C.D., Levoy, M.: Feature-based volume metamorphosis. In: Proceedings of SIGGRAPH 95, pp. 449–456 (1995) CrossRefGoogle Scholar
  15. 15.
    Szewczyk, R., Ferencz, A., Andrews, H., Smith, B.C.: Motion and feature-based video metamorphosis. In: Proceedings of MULTIMEDIA 97, pp. 273–281 (1997) CrossRefGoogle Scholar
  16. 16.
    Zhang, Z., Wang, L., Guo, B., Shum, H.Y.: Feature-based light field morphing. ACM Trans. Graph. 21(3), 457–464 (2002) (Proceedings of SIGGRAPH 02) CrossRefGoogle Scholar
  17. 17.
    Schaefer, S., McPhail, T., Warren, J.: Image deformation using moving least squares. In: ACM Transactions on Graphics (TOG), pp. 533–540 (2006) (Proceedings of SIGGRAPH 06) Google Scholar
  18. 18.
    Lipski, C., Linz, C., Magnor, M.: Belief propagation optical Flow for high-resolution image morphing. In: SIGGRAPH 10 ACM SIGGRAPH 2010 Posters, p. 67 (2010) Google Scholar
  19. 19.
    Kwatra, V., Schödl, A., Essa, I., Turk, G., Bobick, A.: Graph cut textures: image and video synthesis using graph cuts. ACM Trans. Graph. 22(3), 277–286 (2003) (Proceedings of SIGGRAPH 03) CrossRefGoogle Scholar
  20. 20.
    Schödl, A., Szeliski, R., Salesin, D.H., Essa, I.: Video textures. In: Proceedings of SIGGRAPH 00, pp. 489–498 (2000) CrossRefGoogle Scholar
  21. 21.
    Linz, C., Lipski, C., Magnor, M.: Multi-image interpolation based on graph-cuts and symmetric optic flow. In: Proceedings of Vision, Modeling and Visualization (VMV), pp. 115–122. Eurographics Association, Aire-la-Ville (2010) Google Scholar
  22. 22.
    Bhat, P., Zitnick, L., Snavely, N., Agarwala, A., Agrawala, M., Curless, B., Cohen, M., Kang, S.: Using photographs to enhance videos of a static scene. In: Proceedings of Eurographics Symposium on Rendering, pp. 327–338 (2007) Google Scholar
  23. 23.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23(11), 1222–1239 (2001) CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  1. 1.Department of Computer and Information Science, Faculty of Science and TechnologyUniversity of MacauMacaoChina
  2. 2.State Key Laboratory of Computer Science, Institute of SoftwareChinese Academy of SciencesBeijingChina

Personalised recommendations